Searcharxiv⌕ Search

arXiv subjects

Lu Zhang

Publications and source records attributed to Lu Zhang.

At least 271 records · Page 15Linked to original sources
arXiv2023

Cascaded Multi-Modal Mixing Transformers for Alzheimer's Disease Classification with Incomplete Data

Accurate medical classification requires a large number of multi-modal data, and in many cases, different feature types. Previous studies have shown promising results when using multi-modal data, outperforming single-modality models when classifying diseases such as Alzheimer's Disease (AD). However, those models are usually not flexible enough to handle missing modalities. Currently, the most common workaround is discarding samples with missing modalities which leads to considerable data under-utilization. Adding to the fact that labeled medical images are already scarce, the performance of data-driven methods like deep learning can be severely hampered. Therefore, a multi-modal method that can handle missing data in various clinical settings is highly desirable. In this paper, we present Multi-Modal Mixing Transformer (3MAT), a disease classification transformer that not only leverages multi-modal data but also handles missing data scenarios. In this work, we test 3MT for AD and Cognitively normal (CN) classification and mild cognitive impairment (MCI) conversion prediction to progressive MCI (pMCI) or stable MCI (sMCI) using clinical and neuroimaging data. The model uses a novel Cascaded Modality Transformer architecture with cross-attention to incorporate multi-modal information for more informed predictions. We propose a novel modality dropout mechanism to ensure an unprecedented level of modality independence and robustness to handle missing data scenarios. The result is a versatile network that enables the mixing of arbitrary numbers of modalities with different feature types and also ensures full data utilization missing data scenarios. The model is trained and evaluated on the ADNI dataset with the SOTRA performance and further evaluated with the AIBL dataset with missing data.

eess.IV↗
arXiv2023

Locking-free HDG methods for Reissner-Mindlin plates equations on polygonal meshes

We present and analyze a new hybridizable discontinuous Galerkin method (HDG) for the Reissner-Mindlin plate bending system. Our method is based on the formulation utilizing Helmholtz Decomposition. Then the system is decomposed into three problems: two trivial Poisson problems and a perturbed saddle-point problem. We apply HDG scheme for these three problems fully. This scheme yields the optimal convergence rate ($(k+1)$th order in the $\mathrm{L}^2$ norm) which is uniform with respect to plate thickness (locking-free) on general meshes. We further analyze the matrix properties and precondition the new finite element system. Numerical experiments are presented to confirm our theoretical analysis.

math.NA↗
arXiv2023

Hierarchical Semantic Tree Concept Whitening for Interpretable Image Classification

With the popularity of deep neural networks (DNNs), model interpretability is becoming a critical concern. Many approaches have been developed to tackle the problem through post-hoc analysis, such as explaining how predictions are made or understanding the meaning of neurons in middle layers. Nevertheless, these methods can only discover the patterns or rules that naturally exist in models. In this work, rather than relying on post-hoc schemes, we proactively instill knowledge to alter the representation of human-understandable concepts in hidden layers. Specifically, we use a hierarchical tree of semantic concepts to store the knowledge, which is leveraged to regularize the representations of image data instances while training deep models. The axes of the latent space are aligned with the semantic concepts, where the hierarchical relations between concepts are also preserved. Experiments on real-world image datasets show that our method improves model interpretability, showing better disentanglement of semantic concepts, without negatively affecting model classification performance.

cs.CV↗
arXiv2023

Segment Anything Model (SAM) for Radiation Oncology

In this study, we evaluate the performance of the Segment Anything Model (SAM) in clinical radiotherapy. Our results indicate that SAM's 'segment anything' mode can achieve clinically acceptable segmentation results in most organs-at-risk (OARs) with Dice scores higher than 0.7. SAM's 'box prompt' mode further improves the Dice scores by 0.1 to 0.5. Considering the size of the organ and the clarity of its boundary, SAM displays better performance for large organs with clear boundaries but performs worse for smaller organs with unclear boundaries. Given that SAM, a model pre-trained purely on natural images, can handle the delineation of OARs from medical images with clinically acceptable accuracy, these results highlight SAM's robust generalization capabilities with consistent accuracy in automatic segmentation for radiotherapy. In other words, SAM can achieve delineation of different OARs at different sites using a generic automatic segmentation model. SAM's generalization capabilities across different disease sites suggest that it is technically feasible to develop a generic model for automatic segmentation in radiotherapy.

eess.IV↗
arXiv2023

Vibronic fine structure in the nitrogen 1s photoelectron spectra from Franck-Condon simulations II: Indoles

The vibronic coupling effect in nitrogen 1s X-ray photoelectron spectra (XPS) was systematically studied for a family of 17 bicyclic indole molecules by combining Franck-Condon simulations (including the Duschinsky rotation effect) and density functional theory. The simulated vibrationally-resolved spectra of 4 molecules agree well with available experiments. Reliable predictions for this family further allowed us to summarize rules for spectral evolution in response to three types of common structural changes (side chain substitution, CH$\leftrightarrow$N replacement, and isomerization). Interestingly, vibronic properties of amine and imine nitrogen are clearly separated: they show negative and positive $Δ$ZPE (zero-point vibration energy of the core-ionized with respect to the ground state), respectively, indicating flatter and steeper PESs induced by the N 1s ionization; amine N's show stronger mode mixing effects than imine N's; the 1s ionizations on two types of nitrogens led to distinct changes in local bond lengths and angles. The rules are useful for a basic understanding of vibronic coupling in this family, and the precise spectra are useful for future reference and data mining studies.

physics.chem-ph↗
arXiv2023

Identification of Causal Relationship between Amyloid-beta Accumulation and Alzheimer's Disease Progression via Counterfactual Inference

Alzheimer's disease (AD) is a neurodegenerative disorder that is beginning with amyloidosis, followed by neuronal loss and deterioration in structure, function, and cognition. The accumulation of amyloid-beta in the brain, measured through 18F-florbetapir (AV45) positron emission tomography (PET) imaging, has been widely used for early diagnosis of AD. However, the relationship between amyloid-beta accumulation and AD pathophysiology remains unclear, and causal inference approaches are needed to uncover how amyloid-beta levels can impact AD development. In this paper, we propose a graph varying coefficient neural network (GVCNet) for estimating the individual treatment effect with continuous treatment levels using a graph convolutional neural network. We highlight the potential of causal inference approaches, including GVCNet, for measuring the regional causal connections between amyloid-beta accumulation and AD pathophysiology, which may serve as a robust tool for early diagnosis and tailored care.

cs.LG↗
arXiv2023

A sharp Hörmander estimate for multi-parameter and multi-linear Fourier multiplier operators

In this paper, we investigate the Hörmander type theorems for the multi-linear and multi-parameter Fourier multipliers. When the multipliers are characterized by $L^u$-based Sobolev norms for $1<u\le 2$ , our results on the smoothness assumptions are sharp in the multi-parameter and bilinear case. In the multi-parameter and multi-linear case, our results are almost sharp. Moreover, even in the one-parameter and multi-linear case, our results improve earlier ones in the literature.

math.CA↗
arXiv2023

A Weighted Randomized Sparse Kaczmarz Method for Solving Linear Systems

The randomized sparse Kaczmarz method, designed for seeking the sparse solutions of the linear systems $Ax=b$, selects the $i$-th projection hyperplane with likelihood proportional to $\|a_{i}\|_2^2$, where $a_{i}^T$ is $i$-th row of $A$. In this work, we propose a weighted randomized sparse Kaczmarz method, which selects the $i$-th projection hyperplane with probability proportional to $\lvert\langle a_{i},x_{k}\rangle-b_{i}\rvert^p$, where $0<p<\infty$, for possible acceleration. It bridges the randomized Kaczmarz and greedy Kaczmarz by parameter $p$. Theoretically, we show its linear convergence rate in expectation with respect to the Bregman distance in the noiseless and noisy cases, which is at least as efficient as the randomized sparse Kaczmarz method. The superiority of the proposed method is demonstrated via a group of numerical experiments.

math.NA↗
arXiv2023

3rd Place Solution for PVUW2023 VSS Track: A Large Model for Semantic Segmentation on VSPW

In this paper, we introduce 3rd place solution for PVUW2023 VSS track. Semantic segmentation is a fundamental task in computer vision with numerous real-world applications. We have explored various image-level visual backbones and segmentation heads to tackle the problem of video semantic segmentation. Through our experimentation, we find that InternImage-H as the backbone and Mask2former as the segmentation head achieves the best performance. In addition, we explore two post-precessing methods: CascadePSP and Segment Anything Model (SAM). Ultimately, our approach obtains 62.60\% and 64.84\% mIoU on the VSPW test set1 and final test set, respectively, securing the third position in the PVUW2023 VSS track.

cs.CV↗
arXiv2023

Video Diffusion Models with Local-Global Context Guidance

Diffusion models have emerged as a powerful paradigm in video synthesis tasks including prediction, generation, and interpolation. Due to the limitation of the computational budget, existing methods usually implement conditional diffusion models with an autoregressive inference pipeline, in which the future fragment is predicted based on the distribution of adjacent past frames. However, only the conditions from a few previous frames can't capture the global temporal coherence, leading to inconsistent or even outrageous results in long-term video prediction. In this paper, we propose a Local-Global Context guided Video Diffusion model (LGC-VD) to capture multi-perception conditions for producing high-quality videos in both conditional/unconditional settings. In LGC-VD, the UNet is implemented with stacked residual blocks with self-attention units, avoiding the undesirable computational cost in 3D Conv. We construct a local-global context guidance strategy to capture the multi-perceptual embedding of the past fragment to boost the consistency of future prediction. Furthermore, we propose a two-stage training strategy to alleviate the effect of noisy frames for more stable predictions. Our experiments demonstrate that the proposed method achieves favorable performance on video prediction, interpolation, and unconditional video generation. We release code at https://github.com/exisas/LGC-VD.

cs.CV↗
arXiv2023

Discontinuous Galerkin methods for a first-order semi-linear hyperbolic continuum model of a topological resonator dimer array

We present discontinuous Galerkin (DG) methods for solving a first-order semi-linear hyperbolic system, which was originally proposed as a continuum model for a one-dimensional dimer lattice of topological resonators. We examine the energy-conserving or energy-dissipating property in relation to the choices of simple, mesh-independent numerical fluxes. We demonstrate that, with certain numerical flux choices, our DG method achieves optimal convergence in the $L^2$ norm. We provide numerical experiments that validate and illustrate the effectiveness of our proposed numerical methods.

math.NA↗
arXiv2023

Instruction-ViT: Multi-Modal Prompts for Instruction Learning in ViT

Prompts have been proven to play a crucial role in large language models, and in recent years, vision models have also been using prompts to improve scalability for multiple downstream tasks. In this paper, we focus on adapting prompt design based on instruction tuning into a visual transformer model for image classification which we called Instruction-ViT. The key idea is to implement multi-modal prompts (text or image prompt) related to category information to guide the fine-tuning of the model. Based on the experiments of several image captionining tasks, the performance and domain adaptability were improved. Our work provided an innovative strategy to fuse multi-modal prompts with better performance and faster adaptability for visual classification models.

cs.CV↗
arXiv2023

Exploring the Trade-Offs: Unified Large Language Models vs Local Fine-Tuned Models for Highly-Specific Radiology NLI Task

Recently, ChatGPT and GPT-4 have emerged and gained immense global attention due to their unparalleled performance in language processing. Despite demonstrating impressive capability in various open-domain tasks, their adequacy in highly specific fields like radiology remains untested. Radiology presents unique linguistic phenomena distinct from open-domain data due to its specificity and complexity. Assessing the performance of large language models (LLMs) in such specific domains is crucial not only for a thorough evaluation of their overall performance but also for providing valuable insights into future model design directions: whether model design should be generic or domain-specific. To this end, in this study, we evaluate the performance of ChatGPT/GPT-4 on a radiology NLI task and compare it to other models fine-tuned specifically on task-related data samples. We also conduct a comprehensive investigation on ChatGPT/GPT-4's reasoning ability by introducing varying levels of inference difficulty. Our results show that 1) GPT-4 outperforms ChatGPT in the radiology NLI task; 2) other specifically fine-tuned models require significant amounts of data samples to achieve comparable performance to ChatGPT/GPT-4. These findings demonstrate that constructing a generic model that is capable of solving various tasks across different domains is feasible.

cs.CL↗
arXiv2023

Recent Few-Shot Object Detection Algorithms: A Survey with Performance Comparison

The generic object detection (GOD) task has been successfully tackled by recent deep neural networks, trained by an avalanche of annotated training samples from some common classes. However, it is still non-trivial to generalize these object detectors to the novel long-tailed object classes, which have only few labeled training samples. To this end, the Few-Shot Object Detection (FSOD) has been topical recently, as it mimics the humans' ability of learning to learn, and intelligently transfers the learned generic object knowledge from the common heavy-tailed, to the novel long-tailed object classes. Especially, the research in this emerging field has been flourishing in recent years with various benchmarks, backbones, and methodologies proposed. To review these FSOD works, there are several insightful FSOD survey articles [58, 59, 74, 78] that systematically study and compare them as the groups of fine-tuning/transfer learning, and meta-learning methods. In contrast, we review the existing FSOD algorithms from a new perspective under a new taxonomy based on their contributions, i.e., data-oriented, model-oriented, and algorithm-oriented. Thus, a comprehensive survey with performance comparison is conducted on recent achievements of FSOD. Furthermore, we also analyze the technical challenges, the merits and demerits of these methods, and envision the future directions of FSOD. Specifically, we give an overview of FSOD, including the problem definition, common datasets, and evaluation protocols. The taxonomy is then proposed that groups FSOD methods into three types. Following this taxonomy, we provide a systematic review of the advances in FSOD. Finally, further discussions on performance, challenges, and future directions are presented.

cs.CV↗
arXiv2023

An Efficient Spatial-Temporal Trajectory Planner for Autonomous Vehicles in Unstructured Environments

As a core part of autonomous driving systems, motion planning has received extensive attention from academia and industry. However, real-time trajectory planning capable of spatial-temporal joint optimization is challenged by nonholonomic dynamics, particularly in the presence of unstructured environments and dynamic obstacles. To bridge the gap, we propose a real-time trajectory optimization method that can generate a high-quality whole-body trajectory under arbitrary environmental constraints. By leveraging the differential flatness property of car-like robots, we simplify the trajectory representation and analytically formulate the planning problem while maintaining the feasibility of the nonholonomic dynamics. Moreover, we achieve efficient obstacle avoidance with a safe driving corridor for unmodelled obstacles and signed distance approximations for dynamic moving objects. We present comprehensive benchmarks with State-of-the-Art methods, demonstrating the significance of the proposed method in terms of efficiency and trajectory quality. Real-world experiments verify the practicality of our algorithm. We will release our codes for the research community

cs.RO↗
arXiv2023

When Brain-inspired AI Meets AGI

Artificial General Intelligence (AGI) has been a long-standing goal of humanity, with the aim of creating machines capable of performing any intellectual task that humans can do. To achieve this, AGI researchers draw inspiration from the human brain and seek to replicate its principles in intelligent machines. Brain-inspired artificial intelligence is a field that has emerged from this endeavor, combining insights from neuroscience, psychology, and computer science to develop more efficient and powerful AI systems. In this article, we provide a comprehensive overview of brain-inspired AI from the perspective of AGI. We begin with the current progress in brain-inspired AI and its extensive connection with AGI. We then cover the important characteristics for both human intelligence and AGI (e.g., scaling, multimodality, and reasoning). We discuss important technologies toward achieving AGI in current AI systems, such as in-context learning and prompt tuning. We also investigate the evolution of AGI systems from both algorithmic and infrastructural perspectives. Finally, we explore the limitations and future of AGI.

cs.AI↗
arXiv2023

Core-Periphery Principle Guided Redesign of Self-Attention in Transformers

Designing more efficient, reliable, and explainable neural network architectures is critical to studies that are based on artificial intelligence (AI) techniques. Previous studies, by post-hoc analysis, have found that the best-performing ANNs surprisingly resemble biological neural networks (BNN), which indicates that ANNs and BNNs may share some common principles to achieve optimal performance in either machine learning or cognitive/behavior tasks. Inspired by this phenomenon, we proactively instill organizational principles of BNNs to guide the redesign of ANNs. We leverage the Core-Periphery (CP) organization, which is widely found in human brain networks, to guide the information communication mechanism in the self-attention of vision transformer (ViT) and name this novel framework as CP-ViT. In CP-ViT, the attention operation between nodes is defined by a sparse graph with a Core-Periphery structure (CP graph), where the core nodes are redesigned and reorganized to play an integrative role and serve as a center for other periphery nodes to exchange information. We evaluated the proposed CP-ViT on multiple public datasets, including medical image datasets (INbreast) and natural image datasets. Interestingly, by incorporating the BNN-derived principle (CP structure) into the redesign of ViT, our CP-ViT outperforms other state-of-the-art ANNs. In general, our work advances the state of the art in three aspects: 1) This work provides novel insights for brain-inspired AI: we can utilize the principles found in BNNs to guide and improve our ANN architecture design; 2) We show that there exist sweet spots of CP graphs that lead to CP-ViTs with significantly improved performance; and 3) The core nodes in CP-ViT correspond to task-related meaningful and important image patches, which can significantly enhance the interpretability of the trained deep model.

cs.LG↗
arXiv2023

FIT: Frequency-based Image Translation for Domain Adaptive Object Detection

Domain adaptive object detection (DAOD) aims to adapt the detector from a labelled source domain to an unlabelled target domain. In recent years, DAOD has attracted massive attention since it can alleviate performance degradation due to the large shift of data distributions in the wild. To align distributions between domains, adversarial learning is widely used in existing DAOD methods. However, the decision boundary for the adversarial domain discriminator may be inaccurate, causing the model biased towards the source domain. To alleviate this bias, we propose a novel Frequency-based Image Translation (FIT) framework for DAOD. First, by keeping domain-invariant frequency components and swapping domain-specific ones, we conduct image translation to reduce domain shift at the input level. Second, hierarchical adversarial feature learning is utilized to further mitigate the domain gap at the feature level. Finally, we design a joint loss to train the entire network in an end-to-end manner without extra training to obtain translated images. Extensive experiments on three challenging DAOD benchmarks demonstrate the effectiveness of our method.

cs.CV↗